Mastering stock markets with efficient mixture of diversified trading experts
Quantitative stock investment is a fundamental financial task that highly relies on accurate prediction of market status and profitable investment decision making. Despite recent advances in deep learning (DL) have shown stellar performance on capturing trading opportunities in the stochastic stock...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9046 https://ink.library.smu.edu.sg/context/sis_research/article/10049/viewcontent/3580305.3599424_pvoa_cc_by.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-10049 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-100492024-07-25T07:42:23Z Mastering stock markets with efficient mixture of diversified trading experts SUN, Shuo WANG, Xinrun XUE, Wanqi LOU, Xiaoxuan AN, Bo Quantitative stock investment is a fundamental financial task that highly relies on accurate prediction of market status and profitable investment decision making. Despite recent advances in deep learning (DL) have shown stellar performance on capturing trading opportunities in the stochastic stock market, the performance of existing DL methods is unstable with sensitivity to network initialization and hyperparameter selection. One major limitation of existing works is that investment decisions are made based on one individual neural network predictor with high uncertainty, which is inconsistent with the workflow in real-world trading firms. To tackle this limitation, we propose AlphaMix, a novel three-stage mixture-of-experts (MoE) framework for quantitative investment to mimic the efficient bottom-up hierarchical trading strategy design workflow of successful trading companies. In Stage one, we introduce an efficient ensemble learning method, whose computational and memory costs are significantly lower comparing to traditional ensemble methods, to train multiple groups of trading experts with personalised market understanding and trading styles. In Stage two, we collect diversified investment suggestions through building a pool of trading experts utilizing hyperparameter level and initialization level diversity of neural networks for post hoc ensemble construction. In Stage three, we design three different mechanisms, namely as-needed router, with-replacement selection and integrated expert soup, to dynamically pick experts from the expert pool, which takes the responsibility of a portfolio manager. Through extensive experiments on US and Chinese stock markets, we demonstrate that AlphaMix significantly outperforms many state-of-the-art baselines in terms of 7 popular financial criteria. 2023-08-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9046 info:doi/10.1145/3580305.3599424 https://ink.library.smu.edu.sg/context/sis_research/article/10049/viewcontent/3580305.3599424_pvoa_cc_by.pdf http://creativecommons.org/licenses/by/3.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University computational finance deep learning ensemble learning mixture-of-experts quantitative investment stock prediction Artificial Intelligence and Robotics Finance and Financial Management Numerical Analysis and Scientific Computing |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
computational finance deep learning ensemble learning mixture-of-experts quantitative investment stock prediction Artificial Intelligence and Robotics Finance and Financial Management Numerical Analysis and Scientific Computing |
spellingShingle |
computational finance deep learning ensemble learning mixture-of-experts quantitative investment stock prediction Artificial Intelligence and Robotics Finance and Financial Management Numerical Analysis and Scientific Computing SUN, Shuo WANG, Xinrun XUE, Wanqi LOU, Xiaoxuan AN, Bo Mastering stock markets with efficient mixture of diversified trading experts |
description |
Quantitative stock investment is a fundamental financial task that highly relies on accurate prediction of market status and profitable investment decision making. Despite recent advances in deep learning (DL) have shown stellar performance on capturing trading opportunities in the stochastic stock market, the performance of existing DL methods is unstable with sensitivity to network initialization and hyperparameter selection. One major limitation of existing works is that investment decisions are made based on one individual neural network predictor with high uncertainty, which is inconsistent with the workflow in real-world trading firms. To tackle this limitation, we propose AlphaMix, a novel three-stage mixture-of-experts (MoE) framework for quantitative investment to mimic the efficient bottom-up hierarchical trading strategy design workflow of successful trading companies. In Stage one, we introduce an efficient ensemble learning method, whose computational and memory costs are significantly lower comparing to traditional ensemble methods, to train multiple groups of trading experts with personalised market understanding and trading styles. In Stage two, we collect diversified investment suggestions through building a pool of trading experts utilizing hyperparameter level and initialization level diversity of neural networks for post hoc ensemble construction. In Stage three, we design three different mechanisms, namely as-needed router, with-replacement selection and integrated expert soup, to dynamically pick experts from the expert pool, which takes the responsibility of a portfolio manager. Through extensive experiments on US and Chinese stock markets, we demonstrate that AlphaMix significantly outperforms many state-of-the-art baselines in terms of 7 popular financial criteria. |
format |
text |
author |
SUN, Shuo WANG, Xinrun XUE, Wanqi LOU, Xiaoxuan AN, Bo |
author_facet |
SUN, Shuo WANG, Xinrun XUE, Wanqi LOU, Xiaoxuan AN, Bo |
author_sort |
SUN, Shuo |
title |
Mastering stock markets with efficient mixture of diversified trading experts |
title_short |
Mastering stock markets with efficient mixture of diversified trading experts |
title_full |
Mastering stock markets with efficient mixture of diversified trading experts |
title_fullStr |
Mastering stock markets with efficient mixture of diversified trading experts |
title_full_unstemmed |
Mastering stock markets with efficient mixture of diversified trading experts |
title_sort |
mastering stock markets with efficient mixture of diversified trading experts |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2023 |
url |
https://ink.library.smu.edu.sg/sis_research/9046 https://ink.library.smu.edu.sg/context/sis_research/article/10049/viewcontent/3580305.3599424_pvoa_cc_by.pdf |
_version_ |
1814047716347478016 |